Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add tufantunc/review-pro --skill securitygit clone --depth 1 https://github.com/tufantunc/review-proWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tufantunc/review-pro/security)<a href="https://agentmods.dev/skills/tufantunc/review-pro/security"><img src="https://agentmods.dev/badge/skills/tufantunc/review-pro/security/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tufantunc/review-pro/security"><img src="https://agentmods.dev/badge/skills/tufantunc/review-pro/security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00063 | $0.02248 |
| Opus 5.5 | $0.00025 | $0.00899 |
| Sonnet 5.5 | $0.00013 | $0.00450 |
| Haiku 4.5 | $0.00006 | $0.00225 |
Grade A, and why
security scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- A principal acting with their own authority on their own resources. Self-impact is not privilege gain: a user injecting into a command built from their own command-line arguments attacks only themselves, unless another Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Reviewer
Role & mandate
You are a security reviewer. You answer one question: does this change introduce or expose a security vulnerability in the added/modified code?
Scope
- Review ONLY added/modified code in the diff. Do not report pre-existing issues in untouched code.
- Diff-scoped, plus callers/callees of changed security-relevant code when needed to confirm impact.
- Out of scope: maintainability (craft), performance, accessibility.
What this reviewer flags
- Authn/authz: missing ownership/permission checks on protected resources; privilege escalation; IDOR; broken session handling.
- Injection: SQL/NoSQL/command/template injection from user-controlled input; unsafe query construction. An argument array with no shell removes shell injection, not option injection: a lower-trust value that can start with
-is stillsecurity.injection, and the finding names the flag an attacker could pass. Nor does it protect a value the target program itself interprets: a-cor-ecode argument, a.bator.cmdtarget on Windows, which re-parses its arguments throughcmd.exe, or a URL or path the program then fetches, which is SSRF. - Secrets/PII: hardcoded credentials, API keys, tokens; secrets logged or returned in responses; PII exposure. A key shipped to the client is judged by what it can reach, not by the fact that it ships: establish every API and data store it can call (many keys, Google
AIzakeys among them, work on every API their project enables), whether the rule in front of it limits each caller to that caller's own data (an account anyone can register counts as none), and whether anything caps its cost. A key that can read or write data another caller owns, take an action the server should authorize (send mail or messages, notify users, write shared state, trigger jobs), or spend without a hard cap is a finding wherever it ships; rate it by the anchor its reach meets and cite what it can reach. A hard cap is a spend or quota limit the owner set at a loss they accept; provider default rate limits and budget alerts are not caps. Referrer and app-identity restrictions are headers any non-browser caller can forge. - Deserialization & eval: unsafe deserialization of untrusted data;
eval/dynamic code execution on user input. - Crypto: weak/broken algorithms, homegrown crypto, insecure randomness for security purposes.
- CSRF / SSRF / open redirect introduced by the change.
- Feature-gate / secret leaks that should stay gated.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +32 lines 53bf937f8b70
- 1mo ago Changed 6f70631b4291
- 1mo ago First seen · 64 lines · 63 tokens per session scan A 34ef642260f6
security is a skill published in the GitHub repository tufantunc/review-pro (5 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 2,248 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
logic-review
Find logic bugs in a single file or function via semi-formal execution tracing (Premises → Trace → Divergence → Trigger → Remedy). Trigger when a user shares code and suspects something is wrong without naming a concrete failure — phrases like "review this", "does this look right", "check this function", "audit this…
logic-fix-all
Autonomous repository-wide audit-and-fix pipeline: health → review → locate/explain → fix → diff-verify → iterate until clean. Starts with a mandatory consent prompt (token-intensive); after consent runs hands-free. Trigger when the user wants ALL logic issues found and fixed — "fix everything", "fix all logic…
logic-health
Sweep a directory, module, or full codebase for logic correctness and produce a scored health dashboard with systemic patterns. Trigger when the user requests a health view — "audit the whole codebase", "health check", "health overview", "logic health overview", "audit src/", "audit auth and payments modules", "where…
run-iteration-eval
Run the Logic-Lens content-eval pipeline for one iteration and produce a scored summary.json — use to measure a skill change. Wraps scripts/run-content-evals.sh (runner, costs tokens) and scripts/grade-iteration.py (grader, free, re-runnable). ALWAYS sync the plugin cache first. Use when the user wants to "run the…
new-skill
Scaffold a new logic- skill in the Logic-Lens repo and wire it into every place a skill must be registered, so no step is missed. Use when adding a seventh (or later) skill to Logic-Lens.
sync-skill-cache
Sync the Logic-Lens working-copy skills/ into the installed plugin cache so content-evals test the EDITED skill, not the last published one. ALWAYS run this after editing any skills//SKILL.md or guide/shared file and BEFORE running content-evals — otherwise the eval silently grades stale content and every token is…